M2 Mathématiques et Intelligence Artificielle
The flexible course (M1+M2) ‘Mathematics of Artificial Intelligence’ has a dual purpose:
1) to acquire, understand and master a large number of mathematical tools and methods and learn algorithms by offering a wide range of courses in all fields of mathematics and its links (in particular as regards computer science) with artificial intelligence.
2) to allow students to experience from the inside research activity in mathematics in connection with artificial intelligence by tackling unresolved problems from the start of the academic year, a research activity in the form of work placements, as well as courses involving mini-projects.
This courses offers a tailored curriculum designed to help the student formulate and deliver a thesis project with flexibility. The target audience is students of the Master’s (magistère) in Mathematics from Orsay, second year students in Mathematics from ENS Paris-Saclay, as well as foreign students - in particular those with Idex or FMJH travel scholarships. This course is designed as a flexible course which leads to a thesis. A mentoring system is in place to help students plan their programme.
Maitriser et mettre en oeuvre des outils et méthodes mathématiques de haut niveau.
Expliquer clairement une théorie et des résultats mathématiques.
Comprendre et modéliser mathématiquement un problème afin de le résoudre.
Analyser un document de recherche en vue de sa synthèse et de son exploitation.
Maitriser des outils numériques et langages de programmation de référence.
Analyser des données et mettre en oeuvre des simulations numériques.
Connaissance approfondie des théories et outils mathématiques sous-tendant les développements de recherche actuels en apprentissage automatisé et intelligence artificielle.
Expertise sur les enjeux actuels associés, à l'interface théorie mathématique/informatique théorique.
Capacité de mise en oeuvre en pratique, familiarité avec les outils informatiques correspondants.
Expérience de confrontation aux problématiques de la recherche actuelle dans le domaine.
Les débouchés visés sont la thèse en milieu académique ou industriel.
Centre de mathématiques et de leurs applications
Laboratoire de mathématiques d'Orsay
Laboratoire de recherche en informatique.
| Subjects | ECTS | Lecture | directed study | practical class | Lecture/directed study | Lecture/practical class | directed study/practical class | distance-learning course | Project | Supervised studies |
|---|---|---|---|---|---|---|---|---|---|---|
| Méthodes supervisées avancées et data challenge | 5 | 24 | ||||||||
| Méthodes non supervisées avancées | 5 | 24 | ||||||||
| Théorie et applications en apprentissage par renforcement | 5 | 24 | ||||||||
| Subjects | ECTS | Lecture | directed study | practical class | Lecture/directed study | Lecture/practical class | directed study/practical class | distance-learning course | Project | Supervised studies |
|---|---|---|---|---|---|---|---|---|---|---|
| Probabilités et Statistiques en grande dimension | 5 | 24 | ||||||||
| Optimisation | 5 | 24 | ||||||||
| Plateformes et Langages de Programmation en données massives | 5 | 24 | ||||||||
| Signal processing | 2.5 | 20 | ||||||||
| Probabilistic generative models | 2.5 | 20 | ||||||||
| Modélisation en grande dimension | 5 | 24 | ||||||||
| Introduction au Deep Learning | 5 | 24 | ||||||||
| ComputerVision | 5 | 24 | ||||||||
| Speech recognition and NLP | 2.5 | 20 | ||||||||
| Deep Learning pour le NLP | 2.5 | 20 | ||||||||
| Module d'ouverture S1 (UE d'un autre master) | 5 | |||||||||
| Subjects | ECTS | Lecture | directed study | practical class | Lecture/directed study | Lecture/practical class | directed study/practical class | distance-learning course | Project | Supervised studies |
|---|---|---|---|---|---|---|---|---|---|---|
| Guidelines in statistical learning | 4 | 24 | ||||||||
| Statistical learning theory | 4 | 24 | ||||||||
| Statistical theory of algorithmic fairness | 4 | 24 | ||||||||
| Online learning | 4 | 24 | ||||||||
| Modèles graphiques: inférence discrète et apprentissage | 4 | 24 | ||||||||
| Statistique bayésienne et applications | 4 | 24 | ||||||||
| Deep learning avancé | 4 | 24 | ||||||||
| Analyse de données multivariées avancée | 4 | 24 | ||||||||
| Module d'ouverture S2 (UE d'un autre master) | 4 | 24 | ||||||||
| Subjects | ECTS | Lecture | directed study | practical class | Lecture/directed study | Lecture/practical class | directed study/practical class | distance-learning course | Project | Supervised studies |
|---|---|---|---|---|---|---|---|---|---|---|
| Séminaire des étudiants | 2 | |||||||||
| Subjects | ECTS | Lecture | directed study | practical class | Lecture/directed study | Lecture/practical class | directed study/practical class | distance-learning course | Project | Supervised studies |
|---|---|---|---|---|---|---|---|---|---|---|
| Stage ou mémoire | 16 | |||||||||
-
Motivation letter.
-
All transcripts of the years / semesters validated since the high school diploma at the date of application.
-
Curriculum Vitae.
-
Letter of recommendation or internship evaluation.
(A recommendation letter is not mandatory but strongly advisable.) -
Certificate of French (compulsory for non-French speakers).
-
VAP file (obligatory for all persons requesting a valuation of the assets to enter the diploma).
-
Supporting documents :
- Residence permit stating the country of residence of the first country
- Or receipt of request stating the country of first asylum
- Or document from the UNHCR granting refugee status
- Or receipt of refugee status request delivered in France
- Or residence permit stating the refugee status delivered in France
- Or document stating subsidiary protection in France or abroad
- Or document stating temporary protection in France or abroad.